Kai Londenberg
|
b443207c1f
Paged Attention support for FA3 (#1268)
|
hace 1 mes |
Son Nguyen
|
478ee666cc
Make namespace comment consistent (#1305)
|
hace 2 meses |
jayhshah
|
a5a75274bc
FA3 kvcache + split kv + gqa parallelization (#1236)
|
hace 2 meses |
Ying Zhang
|
dfe1a59e4b
Add var-seq-len to FA3 fp16 / bf16 fwd (#1072)
|
hace 5 meses |